NAAINAMar 17

Robust Physics-Guided Diffusion for Full-Waveform Inversion

arXiv:2603.1639369.1h-index: 2
AI Analysis

This work addresses full-waveform inversion for geophysical imaging, presenting an incremental improvement through a novel diffusion-based method.

The paper tackles the problem of full-waveform inversion by developing a robust physics-guided diffusion framework that combines a score-based generative prior with wave-equation simulations, achieving improved reconstruction quality over deterministic optimization baselines and standard diffusion posterior sampling on OpenFWI datasets.

We develop a robust physics-guided diffusion framework for full-waveform inversion that combines a score-based generative prior with likelihood guidance computed through wave-equation simulations. We adopt a transport-based data-consistency potential (Wasserstein-2), incorporating wavefield enhancement via bounded weighting and observation-dependent normalization, thereby improving robustness to amplitude imbalance and time/phase misalignment. On the inference side, we introduce a preconditioned guided reverse-diffusion scheme that adapts the guidance strength and spatial scaling throughout the reverse-time dynamics, yielding a more stable and effective data-consistency guidance step than standard diffusion posterior sampling (DPS). Numerical experiments on OpenFWI datasets demonstrate improved reconstruction quality over deterministic optimization baselines and standard DPS under comparable computational budgets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes